Endogenous Macrodynamics in Algorithmic Recourse

IEEE — Secure and Trustworthy Machine Learning

Patrick Altmeyer

Delft University of Technology

Giovan Angela
Aleksander
Karol
Arie van Deursen
Cynthia C. S. Liem

1/4/23

🥜 In a nutshell …

[…] we run experiments that simulate the application of recourse in practice using various state-of-the-art counterfac- tual generators and find that all of them induce substantial domain and model shifts.

ACKNOWLEDGEMENTS: Views presented in this presentation are my own. I am not affiliated with either Quarto or Posit (RStudio).

Quick Intro

  • Currently 2nd year of PhD in Trustworthy Artificial Intelligence at Delft University of Technology.
  • Working on Counterfactual Explanations and Probabilistic Machine Learning with applications in Finance.
  • Previously, educational background in Economics and Finance and two years at the Bank of England.
  • Enthusiastic about free open-source software, in particular Julia and Quarto.

Motivation

Questions & Answers ❓

Packages I’ve built … 📦

CounterfactualExplanations.jl

Stable Dev Build Status Coverage

CounterfactualExplanations.jl is a package for generating Counterfactual Explanations (CE) and Algorithmic Recourse (AR) for black-box algorithms. Both CE and AR are related tools for explainable artificial intelligence (XAI). While the package is written purely in Julia, it can be used to explain machine learning algorithms developed and trained in other popular programming languages like Python and R. See below for short introduction and other resources or dive straight into the docs.

Turning a nine (9) into a four (4).

A sad 🐱 on its counterfactual path to its cool dog friends.

LaplaceRedux.jl

Stable Dev Build Status Coverage

JuliaCon 22: Effortless Bayesian Deep Learning through Laplace Redux

LaplaceRedux.jl is a small package that can be used for effortless Bayesian Deep Learning and Logistic Regression trough Laplace Approximation. It is inspired by this Python library and its companion paper.

Plugin Approximation (left) and Laplace Posterior (right) for simple artificial neural network.

Simulation of changing posteriour predictive distribution. Image by author.

ConformalPrediction.jl

Stable Dev Build Status Coverage Code Style: Blue ColPrac: Contributor’s Guide on Collaborative Practices for Community Packages Twitter Badge

ConformalPrediction.jl is a package for Uncertainty Quantification (UQ) through Conformal Prediction (CP) in Julia. It is designed to work with supervised models trained in MLJ (Blaom et al. 2020). Conformal Prediction is distribution-free, easy-to-understand, easy-to-use and model-agnostic.

Conformal Prediction in action: Prediction sets for two different samples and changing coverage rates. As coverage grows, so does the size of the prediction sets.

More Resources 📚

Read on …

  • Related blog posts (hosted on this website that itself is built with Quarto and involves lots of Julia content): [1] and [2].
  • Blog post introducing CE: [TDS], [blog].
  • Blog post on Laplace Redux: [TDS], [blog].
  • Blog post on Conformal Prediction: [TDS], [blog].

… or get involved! 🤗

Questions & Answers ❓

Image Sources

  • Quarto logo. Source: Quarto
  • Julia to Quarto animation. Source: author (heavily borrowing from Javis.jl tutorial)

References

A year of using Quarto with Julia — Patrick Altmeyer — CC BY-NC

Blaom, Anthony D., Franz Kiraly, Thibaut Lienart, Yiannis Simillides, Diego Arenas, and Sebastian J. Vollmer. 2020. “MLJ: A Julia Package for Composable Machine Learning.” Journal of Open Source Software 5 (55): 2704. https://doi.org/10.21105/joss.02704.